Llama-3.3-70B-Instruct
9 workload results across 3 hardware configurations.
Fastest config measured by llm-speed (@llmspeed)
19.1 decode tok/s
on 2x RTX 3090 (24GB) via llama.cpp (Q4_K_M). see full run
Signed runs (9 workload results)
2 of 3 runs were measured by llm-speed (@llmspeed); the other one is community-submitted (signed on the submitter's own machine, not measured by llm-speed, and not used for llm-speed verdicts).
A40 (45GB): 48GB, ~45 GiB usable. The label shows what its driver reports as usable, not the 48GB spec.
2x RTX 3090 (24GB)measured by llm-speed
| Workload | Backend | Quant | decode tok/s | prefill tok/s | TTFT | Run | Source |
|---|---|---|---|---|---|---|---|
| chat-short | llama.cpp@0.7.0-dev (build 1, commit f74e2fa) | Q4_K_M | 19.14tok/s | 415.4tok/s | 325ms | r_n93ukk0mkmm | Measured by llm-speed@llmspeed |
| chat-long | llama.cpp@0.7.0-dev (build 1, commit f74e2fa) | Q4_K_M | 18.69tok/s | 939.3tok/s | 3,366ms | r_n93ukk0mkmm | Measured by llm-speed@llmspeed |
| concurrent-decode | llama.cpp@0.7.0-dev (build 1, commit f74e2fa) | Q4_K_M | 19.00tok/s | no data | no data | r_n93ukk0mkmm | Measured by llm-speed@llmspeed |
| agent-trace | llama.cpp@0.7.0-dev (build 1, commit f74e2fa) | Q4_K_M | 18.85tok/s | 2,028.8tok/s | 1,037ms | r_n93ukk0mkmm | Measured by llm-speed@llmspeed |
A40 (45GB)measured by llm-speed
| Workload | Backend | Quant | decode tok/s | prefill tok/s | TTFT | Run | Source |
|---|---|---|---|---|---|---|---|
| chat-short | llama.cpp@0.7.0-dev (build 1, commit ceefd16) | Q4_K_M | 12.99tok/s | 401.0tok/s | 337ms | r_19f64yux97o | Measured by llm-speed@llmspeed |
| chat-long | llama.cpp@0.7.0-dev (build 1, commit ceefd16) | Q4_K_M | 12.67tok/s | 551.4tok/s | 5,735ms | r_19f64yux97o | Measured by llm-speed@llmspeed |
| concurrent-decode | llama.cpp@0.7.0-dev (build 1, commit ceefd16) | Q4_K_M | 12.85tok/s | no data | no data | r_19f64yux97o | Measured by llm-speed@llmspeed |
| agent-trace | llama.cpp@0.7.0-dev (build 1, commit ceefd16) | Q4_K_M | 12.72tok/s | 1,574.5tok/s | 1,344ms | r_19f64yux97o | Measured by llm-speed@llmspeed |
M3 Ultra (60-core GPU) + 96GB unified
| Workload | Backend | Quant | decode tok/s | prefill tok/s | TTFT | Run | Source |
|---|---|---|---|---|---|---|---|
| chat-short | mlx@0.31.3 | 4BIT | 16.78tok/s | 25.09tok/s | 5,420ms | r_sx3a4y9n-m4 | Community-submitted |
Can Llama-3.3-70B-Instruct run on your hardware?
Fastest decode speed on each GPU or Mac, from llm-speed's own runs and community-submitted runs. Each page lists every quant and runtime and labels which runs llm-speed measured.
- 2x RTX 3090 · 19.1 tok/s
- M3 Ultra · 16.8 tok/s
- A40 · 13.0 tok/s
Llama-3.3-70B-Instruct on hardware
Request a Llama-3.3-70B-Instruct run
No measured run yet for these pairs. Vote for the one you want; the most-requested runs go first. See all requests.
We never sell or share your email. Privacy
Compare Llama-3.3-70B-Instruct head-to-head
Buying guides for Llama-3.3-70B-Instruct
Check it for your setup
- Predict your exact setup: estimate whether Llama-3.3-70B-Instruct fits your GPU or Mac at your quant and context, next to measured speeds where we have them.
- Request this pair: ask for a measured Llama-3.3-70B-Instruct run on hardware we have not measured. Requests are ranked by votes.
- Full run table (3 runs): every Llama-3.3-70B-Instruct result we have, with links to each source run.